@codyswann/lisa 2.135.0 → 2.137.0

package/plugins/lisa-wiki-cursor/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "lisa-wiki",
-  "version": "2.135.0",
+  "version": "2.137.0",
   "description": "LLM Wiki — a distributable, git-native markdown knowledge base for Claude Code and Codex",
   "author": {
     "name": "Cody Swann"

package/plugins/src/expo/skills/exploratory-qa/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: exploratory-qa
-description: First-time-user exploratory QA walkthrough for web apps that FEEDS THE LIFECYCLE. Use when asked to experience an app the way a brand-new human user would — landing cold on the home page and clicking through to find anything confusing, broken, or hard to understand (human-facing jargon, contextless extracted data, machine-style labels, slow or unclear loads, late meaningful content, cramped or cut-off UI, inconsistent/non-standard UX, awkward scroll behavior, unclear affordances, dead-end flows that strand a user — e.g. a login page with no way to register or recover a password) across all breakpoints. Instead of writing a report file, it files every finding as a tracked work item via lisa:tracker-write (bugs and usability/UX issues). A `ready` parameter controls whether those tickets are created build-ready (auto-picked-up by lisa:intake) or left in the backlog for human triage (default). For gaps in the automated Playwright test suite, use the e2e-coverage-gaps skill instead.
+description: First-time-user exploratory QA walkthrough for web apps that FEEDS THE LIFECYCLE. Use when asked to experience an app the way a brand-new human user would — landing cold on the home page and clicking through to find anything confusing, broken, or hard to understand (human-facing jargon, contextless extracted data, machine-style labels, slow or unclear loads, late meaningful content, cramped or cut-off UI, inconsistent/non-standard UX, awkward scroll behavior, unclear affordances, dead-end flows that strand a user — e.g. a login page with no way to register or recover a password, or a primary action that drops the user into an incomplete/unsatisfiable state with no way to finish) across all breakpoints. Instead of writing a report file, it files every finding as a tracked work item via lisa:tracker-write (bugs and usability/UX issues). A `ready` parameter controls whether those tickets are created build-ready (auto-picked-up by lisa:intake) or left in the backlog for human triage (default). For gaps in the automated Playwright test suite, use the e2e-coverage-gaps skill instead.
 ---
 
 # Exploratory QA
@@ -80,6 +80,22 @@ mistakes, and tries the obvious thing. Cover at least these dimensions unless th
     no primary action to populate it.
   When the missing counterpart makes a core task impossible for a whole class of users (e.g. a new
   user literally cannot create an account), file a `Bug`; otherwise file a usability `Improvement`.
+- **Action preconditions & incomplete end-states:** an action whose result only makes sense with
+  multiple inputs (compare, merge, combine, bulk-edit) or with some prerequisite met should guide the
+  user to satisfy that precondition — by disabling/explaining it until it is met, by collecting the
+  inputs first (e.g. a selection tray), or by giving the destination an obvious in-place control to
+  complete it. Actually trigger these actions and watch where they land; flag when a primary action:
+  - **Fires under-satisfied and strands the user:** e.g. a per-row "Compare" that navigates to a
+    comparison of a single item, shows an "under limit / add at least 2" notice, but exposes no
+    visible "add another" control — the user is told what is wrong with no in-place means to fix it.
+  - **Lands on an incomplete / empty end-state with no next step:** a results or detail screen that
+    announces it is empty, partial, or "needs more" yet offers no affordance to add, retry, or return
+    to the selection that produced it.
+  - **Is offered where it cannot succeed:** a multi-item action exposed on a single item, or an action
+    left enabled while its precondition (a selection, a minimum count, a required field) is unmet,
+    with no explanation.
+  When the user is left unable to complete the action they started, file a `Bug`; when it eventually
+  works but the path is confusing or roundabout, file a usability `Improvement`.
 - **Visual/layout quality:** cut-off or truncated text, overlap, cramped/crowded density, offscreen or
   unreachable controls, accidental horizontal scroll, awkward empty space. **Do not judge this by
   eyeballing a screenshot alone** — a control clipped by a few pixels or pushed just past a container

package/plugins/src/harper-fabric/skills/exploratory-qa/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: exploratory-qa
-description: First-time-user exploratory QA walkthrough for web apps that FEEDS THE LIFECYCLE. Use when asked to experience an app the way a brand-new human user would — landing cold on the home page and clicking through to find anything confusing, broken, or hard to understand (human-facing jargon, contextless extracted data, machine-style labels, slow or unclear loads, late meaningful content, cramped or cut-off UI, inconsistent/non-standard UX, awkward scroll behavior, unclear affordances, dead-end flows that strand a user — e.g. a login page with no way to register or recover a password) across all breakpoints. Instead of writing a report file, it files every finding as a tracked work item via lisa:tracker-write (bugs and usability/UX issues). A `ready` parameter controls whether those tickets are created build-ready (auto-picked-up by lisa:intake) or left in the backlog for human triage (default). For gaps in the automated Playwright test suite, use the e2e-coverage-gaps skill instead.
+description: First-time-user exploratory QA walkthrough for web apps that FEEDS THE LIFECYCLE. Use when asked to experience an app the way a brand-new human user would — landing cold on the home page and clicking through to find anything confusing, broken, or hard to understand (human-facing jargon, contextless extracted data, machine-style labels, slow or unclear loads, late meaningful content, cramped or cut-off UI, inconsistent/non-standard UX, awkward scroll behavior, unclear affordances, dead-end flows that strand a user — e.g. a login page with no way to register or recover a password, or a primary action that drops the user into an incomplete/unsatisfiable state with no way to finish) across all breakpoints. Instead of writing a report file, it files every finding as a tracked work item via lisa:tracker-write (bugs and usability/UX issues). A `ready` parameter controls whether those tickets are created build-ready (auto-picked-up by lisa:intake) or left in the backlog for human triage (default). For gaps in the automated Playwright test suite, use the e2e-coverage-gaps skill instead.
 ---
 
 # Exploratory QA
@@ -80,6 +80,22 @@ mistakes, and tries the obvious thing. Cover at least these dimensions unless th
     no primary action to populate it.
   When the missing counterpart makes a core task impossible for a whole class of users (e.g. a new
   user literally cannot create an account), file a `Bug`; otherwise file a usability `Improvement`.
+- **Action preconditions & incomplete end-states:** an action whose result only makes sense with
+  multiple inputs (compare, merge, combine, bulk-edit) or with some prerequisite met should guide the
+  user to satisfy that precondition — by disabling/explaining it until it is met, by collecting the
+  inputs first (e.g. a selection tray), or by giving the destination an obvious in-place control to
+  complete it. Actually trigger these actions and watch where they land; flag when a primary action:
+  - **Fires under-satisfied and strands the user:** e.g. a per-row "Compare" that navigates to a
+    comparison of a single item, shows an "under limit / add at least 2" notice, but exposes no
+    visible "add another" control — the user is told what is wrong with no in-place means to fix it.
+  - **Lands on an incomplete / empty end-state with no next step:** a results or detail screen that
+    announces it is empty, partial, or "needs more" yet offers no affordance to add, retry, or return
+    to the selection that produced it.
+  - **Is offered where it cannot succeed:** a multi-item action exposed on a single item, or an action
+    left enabled while its precondition (a selection, a minimum count, a required field) is unmet,
+    with no explanation.
+  When the user is left unable to complete the action they started, file a `Bug`; when it eventually
+  works but the path is confusing or roundabout, file a usability `Improvement`.
 - **Visual/layout quality:** cut-off or truncated text, overlap, cramped/crowded density, offscreen or
   unreachable controls, accidental horizontal scroll, awkward empty space. **Do not judge this by
   eyeballing a screenshot alone** — a control clipped by a few pixels or pushed just past a container

package/plugins/src/openclaw/skills/lisa-openclaw-connect-repo-topic/SKILL.md

@@ -103,8 +103,13 @@ The worker prepares the safe target and launches the CLI; it does not edit files
 
 Route the topic to the dispatcher: set
 `channels.telegram.groups.<group-id>.topics.<topic-id>.agentId = <topic-slug>-dispatch`, keep
-`requireMention = true` and allowlist policy, and add `allowFrom` only when membership must be
-narrower than the group. The topic `systemPrompt` must state the scope mode, treat each native-reply
+allowlist policy, and add `allowFrom` only when membership must be narrower than the group. Leave the
+topic-level `requireMention = false` (the default) so the agent activates on any message — the topic
+is bound 1:1 to this dispatcher, so an @mention carries no routing information and is pure friction.
+Set it to `true` only for a shared-workspace topic where humans also coordinate with each other and
+you don't want every line to spawn a run; the group-level `requireMention` stays `true` regardless.
+See "Mention gating" in [references/repo-topic-config.md](references/repo-topic-config.md) for the
+tradeoff. The topic `systemPrompt` must state the scope mode, treat each native-reply
 root as an independent request context, confirm repo selection only in folder-scoped mode, spawn the
 worker with an explicit repo path, and return the worker result to the topic. Back up
 `~/.openclaw/openclaw.json` before editing and preserve unrelated routes.
@@ -118,11 +123,14 @@ openclaw gateway status
 openclaw channels status --probe
 ```
 
-Then from the target topic: mention the bot and ask for an exact-token reply with **no** file
-changes, commits, PRs, or merges, e.g. `<bot-handle> reply with exactly TELEGRAM-ROUTE-OK`. Confirm
-the visible reply, that the dispatcher spawned the worker, and that the worker ran in the intended
-repo. For folder-scoped topics, also send a request that implies but doesn't name a repo and confirm
-the dispatcher asks for confirmation before proceeding. Do **not** treat `openclaw agent --agent
+Then from the target topic, send a plain message with **no** @mention (the default
+`requireMention = false` means the agent must activate without one) asking for an exact-token reply
+with **no** file changes, commits, PRs, or merges, e.g. `reply with exactly TELEGRAM-ROUTE-OK`.
+Confirm the visible reply, that the dispatcher spawned the worker, and that the worker ran in the
+intended repo. If the topic was deliberately left at `requireMention = true`, mention the bot instead
+(`<bot-handle> reply with exactly TELEGRAM-ROUTE-OK`) and additionally confirm that an un-mentioned
+message is **ignored**. For folder-scoped topics, also send a request that implies but doesn't name a
+repo and confirm the dispatcher asks for confirmation before proceeding. Do **not** treat `openclaw agent --agent
 <id> ...` as proof a topic route works — use the visible topic reply.
 
 ## Output standard

package/plugins/src/openclaw/skills/lisa-openclaw-connect-repo-topic/references/repo-topic-config.md

@@ -77,12 +77,18 @@ repos:
       "groups": {
         "<group-id>": {
           "groupPolicy": "allowlist",
+          // Group-level gate stays on: messages in the group that are NOT inside a
+          // routed topic still require an explicit mention.
           "requireMention": true,
           "allowFrom": ["<telegram-user-id>"],
           "topics": {
             "<topic-id>": {
               "agentId": "<topic-slug>-dispatch",
-              "requireMention": true,
+              // Default false: the topic is bound 1:1 to this agent, so every message
+              // in it is already addressed to the agent — an @mention carries no routing
+              // information. Flip to true only for shared-workspace topics where humans
+              // also coordinate with each other (see "Mention gating" below).
+              "requireMention": false,
               "systemPrompt": "Use the topic's configured scope mode. For single-repo, pass the fixed repo path to <topic-slug>-codex. For folder-scoped, confirm the inferred repo or repo set unless the user already named it explicitly, then pass the explicit repo path(s) to <topic-slug>-codex. Treat each native reply root as an independent request context."
             }
           }
@@ -93,6 +99,28 @@ repos:
 }
 ```
 
+## Mention gating
+
+`requireMention` controls whether a message must @-mention the bot before the agent activates. It is
+set independently at the group level and the topic level; the topic-level value wins for messages
+inside a routed topic.
+
+- **Topic level — default `false`.** A repo-coding topic is bound 1:1 to its dispatcher
+  (`agentId`), so the topic itself already determines the agent. Every message in the topic is
+  addressed to that agent and the @mention adds nothing but friction. This is the "inbox topic"
+  shape: the topic *is* the conversation with the agent.
+- **Set the topic level to `true`** only for a **shared-workspace topic** — one where humans also
+  talk *to each other* (status updates, coordination) and you do not want every stray line to spawn
+  an agent run. The mention then acts as an explicit "this one is for the bot" intent signal.
+- **Group level — keep `true`.** It gates messages posted in the group but outside any routed
+  topic, where there is no 1:1 agent binding to lean on.
+
+Tradeoff to weigh before leaving a topic at `false`: with no mention required, **every** top-level
+message and **every** native reply in the topic wakes the dispatcher (and can spawn a worker run). In
+an inbox topic that is exactly what you want; in a topic people also chat in, it is noise and cost.
+When in doubt, keep code-work topics as dedicated inbox topics (`false`) and push human coordination
+to a separate topic or the group body.
+
 ## Worker launcher form
 
 ```sh

package/plugins/src/rails/skills/exploratory-qa/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: exploratory-qa
-description: First-time-user exploratory QA walkthrough for web apps that FEEDS THE LIFECYCLE. Use when asked to experience an app the way a brand-new human user would — landing cold on the home page and clicking through to find anything confusing, broken, or hard to understand (human-facing jargon, contextless extracted data, machine-style labels, slow or unclear loads, late meaningful content, cramped or cut-off UI, inconsistent/non-standard UX, awkward scroll behavior, unclear affordances, dead-end flows that strand a user — e.g. a login page with no way to register or recover a password) across all breakpoints. Instead of writing a report file, it files every finding as a tracked work item via lisa:tracker-write (bugs and usability/UX issues). A `ready` parameter controls whether those tickets are created build-ready (auto-picked-up by lisa:intake) or left in the backlog for human triage (default). For gaps in the automated Playwright test suite, use the e2e-coverage-gaps skill instead.
+description: First-time-user exploratory QA walkthrough for web apps that FEEDS THE LIFECYCLE. Use when asked to experience an app the way a brand-new human user would — landing cold on the home page and clicking through to find anything confusing, broken, or hard to understand (human-facing jargon, contextless extracted data, machine-style labels, slow or unclear loads, late meaningful content, cramped or cut-off UI, inconsistent/non-standard UX, awkward scroll behavior, unclear affordances, dead-end flows that strand a user — e.g. a login page with no way to register or recover a password, or a primary action that drops the user into an incomplete/unsatisfiable state with no way to finish) across all breakpoints. Instead of writing a report file, it files every finding as a tracked work item via lisa:tracker-write (bugs and usability/UX issues). A `ready` parameter controls whether those tickets are created build-ready (auto-picked-up by lisa:intake) or left in the backlog for human triage (default). For gaps in the automated Playwright test suite, use the e2e-coverage-gaps skill instead.
 ---
 
 # Exploratory QA
@@ -80,6 +80,22 @@ mistakes, and tries the obvious thing. Cover at least these dimensions unless th
     no primary action to populate it.
   When the missing counterpart makes a core task impossible for a whole class of users (e.g. a new
   user literally cannot create an account), file a `Bug`; otherwise file a usability `Improvement`.
+- **Action preconditions & incomplete end-states:** an action whose result only makes sense with
+  multiple inputs (compare, merge, combine, bulk-edit) or with some prerequisite met should guide the
+  user to satisfy that precondition — by disabling/explaining it until it is met, by collecting the
+  inputs first (e.g. a selection tray), or by giving the destination an obvious in-place control to
+  complete it. Actually trigger these actions and watch where they land; flag when a primary action:
+  - **Fires under-satisfied and strands the user:** e.g. a per-row "Compare" that navigates to a
+    comparison of a single item, shows an "under limit / add at least 2" notice, but exposes no
+    visible "add another" control — the user is told what is wrong with no in-place means to fix it.
+  - **Lands on an incomplete / empty end-state with no next step:** a results or detail screen that
+    announces it is empty, partial, or "needs more" yet offers no affordance to add, retry, or return
+    to the selection that produced it.
+  - **Is offered where it cannot succeed:** a multi-item action exposed on a single item, or an action
+    left enabled while its precondition (a selection, a minimum count, a required field) is unmet,
+    with no explanation.
+  When the user is left unable to complete the action they started, file a `Bug`; when it eventually
+  works but the path is confusing or roundabout, file a usability `Improvement`.
 - **Visual/layout quality:** cut-off or truncated text, overlap, cramped/crowded density, offscreen or
   unreachable controls, accidental horizontal scroll, awkward empty space. **Do not judge this by
   eyeballing a screenshot alone** — a control clipped by a few pixels or pushed just past a container